Hyperspectral Image Classification based on Co-training

Zhijun Zheng,Yanbin Peng 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.12

The abundant information available in hyperspectral image has provided important opportunities for land-cover classification and recognition. However, “Curse of dimensionality” and small training sample set are two difficulties which hinder the improvement of computational efficiency and classification precision. In this paper, we present a co-training based method on hyperspectral image classification. Firstly, two views of samples are generated through two kinds of dimensionality reduction methods. After that, the co-training process is viewed as combinative label propagation over two independent views. Experimental results on real hyperspectral image show that the proposed method has better performance than the other state-of-the-art methods.

Zn Sorption to Biogenic Bixbyite-like Mn₂O₃ Produced by Bacillus Cua Isolated from Soil: Xafs Study with Constraints on Sorption Mechanism

Zhijun Zhang,Hui Yin,Wenfeng Tan,Luuk K Koopal,Lirong Zheng,Xionghan Feng,Fan Liu 한국토양비료학회 2014 한국토양비료학회 학술발표회 초록집 Vol.2014 No.6

Manifold Sparse Coding Based Hyperspectral Image Classification

Yanbin Peng,Zhijun Zheng,Jiming Li,Zhigang Pan,Xiaoyong Li,Zhinian Zhai 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.12

Hyperspectral image classification has received an increasing amount of interest in recent years. However, when representing pixels as vectors, the dimensionality of feature space is high, which causes “curse of dimensionality” problem. In this paper, in order to alleviate the impact of above problem, a manifold sparse coding method is proposed. Firstly, matrix decomposition technique is used to find a concept set and calculates relative data projection in the concept set. Secondly, manifold learning regularization is imported into objective function to capture the intrinsic geometric structure in the data. Finally, LASSO regularization is used to obtain sparse representation of data projection. Experimental results on real hyperspectral image show that the proposed method has better performance than the other state-of-the-art methods.

Gestational weight gain of multiparas and risk of primary preeclampsia: a retrospective cohort study in Shanghai

Chen Chao,Lei Zhijun,Xiong Yaoxi,Ni Meng,He Biwei,Gao Jing,Zheng Panchan,Xie Xianjing,He Chengrong,Yang Xingyu,Cheng Weiwei 대한고혈압학회 2023 Clinical Hypertension Vol.29 No.-

Background In all studies conducted so far, there was no report about the correlation between excessive gestational weight gain (GWG) and the risk of preeclampsia (PE) in multiparas, especially considering that multiparity is a protective factor for both excessive GWG and PE. Thus, the aim of this retrospective cohort study was to determine whether GWG of multiparas is associated with the increased risk of PE. Methods This was a study with 15,541 multiparous women who delivered in a maternity hospital in Shanghai from 2017 to 2021, stratifed by early-pregnancy body mass index (BMI) category. Early-pregnancy body weight, height, week-specifc and total gestational weight gain as well as records of antenatal care were extracted using electronic medical records, and antenatal weight gain measurements were standardized into gestational age-specifc z scores. Results Among these 15,541 multiparous women, 534 (3.44%) developed preeclampsia. The odds of preeclampsia increased by 26% with every 1 z score increase in pregnancy weight gain among normal weight women and by 41% among overweight or obese women. For normal weight women, pregnant women with preeclampsia gained more weight than pregnant women without preeclampsia beginning at 25 weeks of gestation, while accelerated weight gain was more obvious in overweight or obese women after 25 weeks of gestation. Conclusions In conclusion, excessive GWG in normal weight and overweight or obese multiparas was strongly associated with the increased risk of preeclampsia. In parallel, the appropriate management and control of weight gain, especially in the second and third trimesters, may lower the risk of developing preeclampsia.

Hyperspectral Image Classification by Fusion of Multiple Classifiers

Yanbin Peng,Zhigang Pan,Zhijun Zheng,Xiaoyong Li 보안공학연구지원센터 2016 International Journal of Database Theory and Appli Vol.9 No.2

Hyperspectral image mostly have very large amounts of data which makes the computational cost and subsequent classification task a difficult issue. Firstly, to solve the problem of computational complexity, spectral clustering algorithm is imported to select efficient bands for subsequent classification task. Secondly, due to lack of labeled training sample points, this paper proposes a new algorithm that combines support vector machines and Bayesian classifier to create a discriminative/generative hyperspectral image classification method using the selected features. Experimental results on real hyperspectral image show that the proposed method has better performance than the other state-of-the-art methods.

MLSE-Net: Multi-level Semantic Enriched Network for Medical Image Segmentation

Di Gai,Heng Luo,Jing He, Baogang Xie,Pengxiang Su,Zheng Huang,Song Zhang,Zhijun Tu 한국인터넷정보학회 2023 KSII Transactions on Internet and Information Syst Vol.17 No.9

Medical image segmentation techniques based on convolution neural networks indulge in feature extraction triggering redundancy of parameters and unsatisfactory target localization, which outcomes in less accurate segmentation results to assist doctors in diagnosis. In this paper, we propose a multi-level semantic-rich encoding-decoding network, which consists of a Pooling-Conv-Former (PCFormer) module and a Cbam-Dilated-Transformer (CDT) module. In the PCFormer module, it is used to tackle the issue of parameter explosion in the conservative transformer and to compensate for the feature loss in the down-sampling process. In the CDT module, the Cbam attention module is adopted to highlight the feature regions by blending the intersection of attention mechanisms implicitly, and the Dilated convolution-Concat (DCC) module is designed as a parallel concatenation of multiple atrous convolution blocks to display the expanded perceptual field explicitly. In addition, Multi-Head Attention-DwConv-Transformer (MDTransformer) module is utilized to evidently distinguish the target region from the background region. Extensive experiments on medical image segmentation from Glas, SIIM-ACR, ISIC and LGG demonstrated that our proposed network outperforms existing advanced methods in terms of both objective evaluation and subjective visual performance.

Experimental study on solidification of uranium tailings by microbial grouting combined with electroosmosis

Deng Jinxiang,Li Mengjie,Tian Yakun,Wu Lingling,Hu Lin,Zhang Zhijun,Zheng Huaimiao 한국원자력학회 2023 Nuclear Engineering and Technology Vol.55 No.12

The present microbial reinforcement of rock and soil exhibits limitations, such as uneven reinforcement effectiveness and low calcium carbonate generation rate, resulting in limited solidification strength. This study introduces electroosmosis as a standard microbial grouting reinforcement technique and investigates its solidification effects on microbial-reinforced uranium tailings. The most effective electroosmosis effect on uranium tailings occurs under a potential gradient of 1.25 V/cm. The findings indicate that a weak electric field can effectively promote microbial growth and biological activity and accelerate bacterial metabolism. The largest calcium carbonate production occurred under the gradient of 0.5 V/cm, featuring a good crystal combination and the best cementation effect. Staged electroosmosis and electrode conversion efficiently drive the migration of anions and cations. Under electroosmosis, the cohesion of uranium tailings reinforced by microorganisms increased by 37.3% and 64.8% compared to those reinforced by common microorganisms and undisturbed uranium tailings, respectively. The internal friction angle is also improved, significantly enhancing the uniformity of reinforcement and a denser and stronger microscopic structure. This research demonstrates that MICP technology enhances the solidification effects and uniformity of uranium tailings, providing a novel approach to maintaining the safety and stability of uranium tailings dams